Nathan Lambert Sees Investment in RL Data and Real-World Evaluations

What happened

Nathan Lambert says the data industry has grown, but low-quality output can amplify behaviors such as reward hacking. He is advising Mercor on research into sample-efficient data for RL and says the field needs stronger evaluation science and benchmarks tied to areas of clear economic value. Lambert expects major investment around frontier labs in open inference, open post-training and data, with opportunities to build on open models.

The story so far

Nathan Lambert says he is advising Mercor on research into sample-efficient data for reinforcement learning (RL), with stronger evaluation science and benchmarks tied to areas of clear economic value as priorities for the field. Lambert says the data industry has grown, but low-quality output can amplify behaviors such as reward hacking. He expects major investment in open inference, open post-training and data around frontier labs, focused on expertise in representative real-world evaluations and synthetic data methods for scaling training data around those evaluations. He also sees opportunities to build on open models.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights